Forecasting functional time series using weighted likelihood methodology

Functional time series whose sample elements are recorded sequentially over time are frequently encountered with increasing technology. Recent studies have shown that analyzing and forecasting of functional time series can be performed easily using functional principal component analysis and existing univariate/multivariate time series models. However, the forecasting performance of such functional time series models may be affected by the presence of outlying observations which are very common in many scientific fields. Outliers may distort the functional time series model structure, and thus, the underlying model may produce high forecast errors. We introduce a robust forecasting technique based on weighted likelihood methodology to obtain point and interval forecasts in functional time series in the presence of outliers. The finite sample performance of the proposed method is illustrated by Monte Carlo simulations and four real-data examples. Numerical results reveal that the proposed method exhibits superior performance compared with the existing method(s).     

Functional time series approach for forecasting very short-term electricity demand

This empirical paper presents a number of functional modelling and forecasting methods for predicting very short-term (such as minute-by-minute) electricity demand. The proposed functional methods slice a seasonal univariate time series (TS) into a TS of curves; reduce the dimensionality of curves by applying functional principal component analysis before using a univariate TS forecasting method and regression techniques. As data points in the daily electricity demand are sequentially observed, a forecast updating method can greatly improve the accuracy of point forecasts. Moreover, we present a non-parametric bootstrap approach to construct and update prediction intervals, and compare the point and interval forecast accuracy with some naive benchmark methods. The proposed methods are illustrated by the half-hourly electricity demand from Monday to Sunday in South Australia.     

A diagnostic statistic for functional-coefficient autoregressive models

In this paper, functional coefficient autoregressive (FAR) models proposed by Chen and Tsay (1993) are considered. We propose a diagnostic statistic for FAR models constructed by comparing between parametric and nonparametric estimators of the functional form of the FAR models. We show asymptotic properties of our statistic mathematically and it can be applied to the estimation of the delay parameter and the specification of the functional form of FAR models.     

INDEX TO VOLUME 8 (1 990)

This article provides a simple shrinkage representation that describes the operational characteristics of various forecasting methods designed for a large number of orthogonal predictors (such as principal components). These methods include pretest methods, Bayesian model averaging, empirical Bayes, and bagging. We compare empirically forecasts from these methods with dynamic factor model (DFM) forecasts using a U.S. macroeconomic dataset with 143 quarterly variables spanning 1960–2008. For most series, including measures of real economic activity, the shrinkage forecasts are inferior to the DFM forecasts. This article has online supplementary material.     

Bayesian covariance estimation and inference in latent Gaussian process models

This paper describes inference methods for functional data under the assumption that the functional data of interest are smooth latent functions, characterized by a Gaussian process, which have been observed with noise over a finite set of time points. The methods we propose are completely specified in a Bayesian environment that allows for all inferences to be performed through a simple Gibbs sampler. Our main focus is in estimating and describing uncertainty in the covariance function. However, these models also encompass functional data estimation, functional regression where the predictors are latent functions, and an automatic approach to smoothing parameter selection. Furthermore, these models require minimal assumptions on the data structure as the time points for observations do not need to be equally spaced, the number and placement of observations are allowed to vary among functions, and special treatment is not required when the number of functional observations is less than the dimensionality of those observations. We illustrate the effectiveness of these models in estimating latent functional data, capturing variation in the functional covariance estimate, and in selecting appropriate smoothing parameters in both a simulation study and a regression analysis of medfly fertility data.     

On the Empirical Likelihood Ratio for Smooth Functions of M-functionals

It is known that the empirical likelihood ratio can be used to construct confidence regions for smooth functions of the mean, Fréchet differentiable statistical functionals and for a class of M-functionals. In this paper, we argue that this use can be extended to the class of functionals which are smooth functions of M-functionals. In particular, we find the conditions under which the empirical log-likelihood ratio for this kind of functionals admits a χ² approxima tion. Furthermore, we investigate, by simulation methods, the related approximation error in some contexts of practical interest.     

Comparing Possibly Misspecified Forecasts

Abstract

Recent work has emphasized the importance of evaluating estimates of a statistical functional (such as a conditional mean, quantile, or distribution) using a loss function that is consistent for the functional of interest, of which there is an infinite number. If forecasters all use correctly specified models free from estimation error, and if the information sets of competing forecasters are nested, then the ranking induced by a single consistent loss function is sufficient for the ranking by any consistent loss function. This article shows, via analytical results and realistic simulation-based analyses, that the presence of misspecified models, parameter estimation error, or nonnested information sets, leads generally to sensitivity to the choice of (consistent) loss function. Thus, rather than merely specifying the target functional, which narrows the set of relevant loss functions only to the class of loss functions consistent for that functional, forecast consumers or survey designers should specify the single specific loss function that will be used to evaluate forecasts. An application to survey forecasts of U.S. inflation illustrates the results.     

A Note on Generalized Functional Linear Model and Its Application

Motivated by a biomarker study for colorectal neoplasia, we consider generalized functional linear models where the functional predictors are measured with errors at discrete design points. Assuming that the true functional predictor and the slope function are smooth, we investigate a two-step estimating procedure where both the true functional predictor and the slope function are estimated through spline smoothing. The operating characteristics of the proposed method are derived; the usefulness of the proposed method is illustrated by a simulation study as well as data analysis for the motivating colorectal neoplasia study.     

Functional variable selection via Gram–Schmidt orthogonalization for multiple functional linear regression

ABSTRACT

Functional linear model is of great practical importance, as exemplified by applications in high-throughput studies such as meteorological and biomedical research. In this paper, we propose a new functional variable selection procedure, called functional variable selection via Gram–Schmidt (FGS) orthogonalization, for a functional linear model with a scalar response and multiple functional predictors. Instead of the regularization methods, FGS takes into account the similarity between the functional predictors in a data-driven way and utilizes the technique of Gram–Schmidt orthogonalization to remove the irrelevant predictors. FGS can successfully discriminate between the relevant and the irrelevant functional predictors to achieve a high true positive ratio without including many irrelevant predictors, and yield explainable models, which offers a new perspective for the variable selection method in the functional linear model. Simulation studies are carried out to evaluate the finite sample performance of the proposed method, and also a weather data set is analysed.     

Forecasting Equity Premium: Global Historical Average Versus Local Historical Average and Constraints

The equity premium, return on equity minus return on risk-free asset, is expected to be positive. We consider imposing such positivity constraint in local historical average (LHA) in nonparametric kernel regression framework. It is also extended to the semiparametric single index model when multiple predictors are used. We construct the constrained LHA estimator via an indicator function which operates as “model-selection” between the unconstrained LHA and the bound of the constraint (zero for the positivity constraint). We smooth the indicator function by bagging, which operates as “model-averaging” and yields a combined forecast of unconstrained LHA forecasts and the bound of the constraint. The local combining weights are determined by the probability that the constraint is binding. Asymptotic properties of the constrained LHA estimators without and with bagging are established, which show how the positive constraint and bagging can help reduce the asymptotic variance and mean squared errors. Monte Carlo simulations are conducted to show the finite sample behavior of the asymptotic properties. In predicting U.S. equity premium, we show that substantial nonlinearity can be captured by LHA and that the local positivity constraint can improve out-of-sample prediction of the equity premium.     

Approximation spline de la prevision d'un processus fonctionnel autorégressif d'ordre 1

ABSTRACT We present a method to approximate and forecast, on an entire interval, a continuous-time process. For this purpose, we use the modelization of ARH(l) processes, defined by Bosq (1991). We deal with the practical problem of the discretization of the observed trajectories and approximate them by means of spline functions. We show by simulations that for well-chosen smoothing parameters, good prediction can be obtained in comparison with the “predictable” part of the process. Finally, we apply this model to forecast road traffic and compare it with a SARIMA model.     

Functional Autoregression for Sparsely Sampled Data

We develop a hierarchical Gaussian process model for forecasting and inference of functional time series data. Unlike existing methods, our approach is especially suited for sparsely or irregularly sampled curves and for curves sampled with nonnegligible measurement error. The latent process is dynamically modeled as a functional autoregression (FAR) with Gaussian process innovations. We propose a fully nonparametric dynamic functional factor model for the dynamic innovation process, with broader applicability and improved computational efficiency over standard Gaussian process models. We prove finite-sample forecasting and interpolation optimality properties of the proposed model, which remain valid with the Gaussian assumption relaxed. An efficient Gibbs sampling algorithm is developed for estimation, inference, and forecasting, with extensions for FAR(p) models with model averaging over the lag p. Extensive simulations demonstrate substantial improvements in forecasting performance and recovery of the autoregressive surface over competing methods, especially under sparse designs. We apply the proposed methods to forecast nominal and real yield curves using daily U.S. data. Real yields are observed more sparsely than nominal yields, yet the proposed methods are highly competitive in both settings. Supplementary materials, including R code and the yield curve data, are available online.     

Forecasting Vector ARMA Processes With Systematically Missing Observations

The following two predictors are compared for time series with systematically missing observations: (a) A time series model is fitted to the full series X_t , and forecasts are based on this model, (b) A time series model is fitted to the series with systematically missing observations Y _τ, and forecasts are based on the resulting model. If the data generation processes are known vector autoregressive moving average (ARMA) processes, the first predictor is at least as efficient as the second one in a mean squared error sense. Conditions are given for the two predictors to be identical. If only the ARMA orders of the generation processes are known and the coefficients are estimated, or if the process orders and coefficients are estimated, the first predictor is again, in general, superior. There are, however, exceptions in which the second predictor, using seemingly less information, may be better. These results are discussed, using both asymptotic theory and small sample simulations. Some economic time series are used as illustrative examples.     

Functional analysis of high-content high-throughput imaging data

High-content automated imaging platforms allow the multiplexing of several targets simultaneously to generate multi-parametric single-cell data sets over extended periods of time. Typically, standard simple measures such as mean value of all cells at every time point are calculated to summarize the temporal process, resulting in loss of time dynamics of the single cells. Multiple experiments are performed but observation time points are not necessarily identical, leading to difficulties when integrating summary measures from different experiments. We used functional data analysis to analyze continuous curve data, where the temporal process of a response variable for each single cell can be described using a smooth curve. This allows analyses to be performed on continuous functions, rather than on original discrete data points. Functional regression models were applied to determine common temporal characteristics of a set of single cell curves and random effects were employed in the models to explain variation between experiments. The aim of the multiplexing approach is to simultaneously analyze the effect of a large number of compounds in comparison to control to discriminate between their mode of action. Functional principal component analysis based on T-statistic curves for pairwise comparison to control was used to study time-dependent compound effects.     

Combination of multiple functional markers to improve diagnostic accuracy

Combination of multiple biomarkers to improve diagnostic accuracy is meaningful for practitioners and clinicians, and are attractive to lots of researchers. Nowadays, with development of modern techniques, functional markers such as curves or images, play an important role in diagnosis. There exists rich literature developing combination methods for continuous scalar markers. Unfortunately, only sporadic works have studied how functional markers affect diagnosis in the literature. Moreover, no publication can be found to do combination of multiple functional markers to improve the diagnostic accuracy. It is impossible to apply scalar combination methods to the multiple functional markers directly because of infinite dimensionality of functional markers. In this article, we propose a one-dimension scalar feature motivated by square loss distance, as an alternative of the original functional curve in the sense that, it can retain information to the most extent. The square loss distance is defined as the function of projection scores generated from functional principal component decomposition. Then existing variety of scalar combination methods can be applied to scalar features of functional markers after dimension reduction to improve the diagnostic accuracy. Area under the receiver operating characteristic curve and Youden index are used to assess performances of various methods in numerical studies. We also analyzed the high- or low- hospital admissions due to respiratory diseases between 2010 and 2017 in Hong Kong by combining weather conditions and media information, which are regarded as functional markers. Finally, we provide an R function for convenient application.     

Coherent mortality forecasting by the weighted multilevel functional principal component approach

In human mortality modelling, if a population consists of several subpopulations it can be desirable to model their mortality rates simultaneously while taking into account the heterogeneity among them. The mortality forecasting methods tend to result in divergent forecasts for subpopulations when independence is assumed. However, under closely related social, economic and biological backgrounds, mortality patterns of these subpopulations are expected to be non-divergent in the future. In this article, we propose a new method for coherent modelling and forecasting of mortality rates for multiple subpopulations, in the sense of nondivergent life expectancy among subpopulations. The mortality rates of subpopulations are treated as multilevel functional data and a weighted multilevel functional principal component (wMFPCA) approach is proposed to model and forecast them. The proposed model is applied to sex-specific data for nine developed countries, and the results show that, in terms of overall forecasting accuracy, the model outperforms the independent model and the Product-Ratio model as well as the unweighted multilevel functional principal component approach.     

Multi-step forecasts from threshold ARMA models using asymmetric loss functions

The forecasts generation from nonlinear time series models is investigated under general loss functions. After presenting the main results and some relevant features of these functions, the Linex loss has been used to generate multi-step forecasts from threshold autoregressive moving average models showing their main properties and some results connected to a proper transformation of the forecast errors. A simulation exercise highlights interesting properties of the proposed predictors, both in terms of their bias and their distribution, further clarifying how the Linex predictor can be helpful in empirical applications.     

Function-on-function regression for two-dimensional functional data

ABSTRACT

We present methods for modeling and estimation of a concurrent functional regression when the predictors and responses are two-dimensional functional datasets. The implementations use spline basis functions and model fitting is based on smoothing penalties and mixed model estimation. The proposed methods are implemented in available statistical software, allow the construction of confidence intervals for the bivariate model parameters, and can be applied to completely or sparsely sampled responses. Methods are tested to data in simulations and they show favorable results in practice. The usefulness of the methods is illustrated in an application to environmental data.     

Sufficient reduction methods for multivariate time-dependent health surveillance data

ABSTRACT

Early detection with a low false alarm rate (FAR) is the main aim of outbreak detection as used in public health surveillance or in regard to bioterrorism. Multivariate surveillance is preferable to univariate surveillance since correlation between series (CBS) is recognized and incorporated. Sufficient reduction has proved a promising method for handling CBS, but has not previously been used when correlation within series (CWS) is present. Here we develop sufficient reduction methods for reducing a p-dimensional multivariate series to a univariate series of statistics shown to be sufficient to monitor a sudden, but persistent, shift in the multivariate series mean. Correlation both within and between series is taken into account, as public health data typically exhibit both forms of association. Simultaneous and lagged changes and different shift sizes are investigated. A one-sided exponentially weighted moving average chart is used as a tool for detection of a change. The performance of the proposed method is compared with existing sufficient reduction methods, the parallel univariate method and both VarR and Z charts. A simulation study using bivariate normal autoregressive data shows that the new method gives shorter delays and a lower FAR than other methods, which have high FARs when CWS is clearly present.